[Misc] Enhance prefix-caching benchmark tool #6568
Conversation
- Added support for using real ShareGPT data for testing. - Introduced new parameters to duplicate prompts for more extensive testing. - Implemented benchmark support against prompts with varying input token lengths. - Added functionality to sort or shuffle data, simulating real-world traffic patterns. This update allows for more accurate and flexible performance testing on the prefix cache
|
👋 Hi! Thank you for contributing to the vLLM project. Once the PR is approved and ready to go, please make sure to run full CI as it is required to merge (or just use auto-merge). To run full CI, you can do one of these:
🚀 |
|
amazing!
|
|
Thanks! |
Let me try to reproduce these two issues |
Please check back if you do 🙏. In the meantime, I will also try to reproduce the issue with your PR. |
|
@KrishnaM251 @hibukipanim I have not verified the correctness or consistency in my test yet. It's great to know you found such issue. This PR right now focusing on more real world data, especially the efficiency between different prompt size. It may not fix the correctness issue but I will definitely try to help check the problem you mentioned as I can |
|
@robertgshaw2-neuralmagic @simon-mo kindly ping |
Signed-off-by: Alvant <alvasian@yandex.ru>
I update the prefix-caching benchmark tool with following new features
This update allows for more accurate and flexible performance testing on the prefix cache
BEFORE SUBMITTING, PLEASE READ THE CHECKLIST BELOW AND FILL IN THE DESCRIPTION ABOVE
PR Checklist (Click to Expand)
Thank you for your contribution to vLLM! Before submitting the pull request, please ensure the PR meets the following criteria. This helps vLLM maintain the code quality and improve the efficiency of the review process.
PR Title and Classification
Only specific types of PRs will be reviewed. The PR title is prefixed appropriately to indicate the type of change. Please use one of the following:
[Bugfix]for bug fixes.[CI/Build]for build or continuous integration improvements.[Doc]for documentation fixes and improvements.[Model]for adding a new model or improving an existing model. Model name should appear in the title.[Frontend]For changes on the vLLM frontend (e.g., OpenAI API server,LLMclass, etc.)[Kernel]for changes affecting CUDA kernels or other compute kernels.[Core]for changes in the core vLLM logic (e.g.,LLMEngine,AsyncLLMEngine,Scheduler, etc.)[Hardware][Vendor]for hardware-specific changes. Vendor name should appear in the prefix (e.g.,[Hardware][AMD]).[Misc]for PRs that do not fit the above categories. Please use this sparingly.Note: If the PR spans more than one category, please include all relevant prefixes.
Code Quality
The PR need to meet the following code quality standards:
format.shto format your code.docs/source/if the PR modifies the user-facing behaviors of vLLM. It helps vLLM user understand and utilize the new features or changes.Notes for Large Changes
Please keep the changes as concise as possible. For major architectural changes (>500 LOC excluding kernel/data/config/test), we would expect a GitHub issue (RFC) discussing the technical design and justification. Otherwise, we will tag it with
rfc-requiredand might not go through the PR.What to Expect for the Reviews
The goal of the vLLM team is to be a transparent reviewing machine. We would like to make the review process transparent and efficient and make sure no contributor feel confused or frustrated. However, the vLLM team is small, so we need to prioritize some PRs over others. Here is what you can expect from the review process:
action-requiredlabel on the PR if there are changes required. The contributor should address the comments and ping the reviewer to re-review the PR.Thank You
Finally, thank you for taking the time to read these guidelines and for your interest in contributing to vLLM. Your contributions make vLLM a great tool for everyone!